wiki-query
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill creates an indirect prompt injection vulnerability surface by reading and processing data from potentially untrusted local wiki files.
- Ingestion points: The skill reads 'SCHEMA.md', 'wiki/index.md', and various markdown files within 'wiki/pages/' to generate answers for the user.
- Boundary markers: There are no explicit boundary markers, delimiters, or system-level instructions instructing the agent to ignore any commands or instructions found within the wiki pages during the synthesis phase.
- Capability inventory: The skill possesses the capability to read any file within the identified wiki root and write or append to 'wiki/pages/', 'wiki/index.md', and 'wiki/log.md'.
- Sanitization: There is no evidence of sanitization, escaping, or validation of the wiki content before it is processed by the agent.
Audit Metadata